Agent skill
council-debug
Use for systematic debugging and root cause analysis with both Codex and Gemini. Triggers on "council debug", "council root cause", "have council investigate this bug", "council find the issue".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/council-debug
SKILL.md
Council Debug Skill
Systematic debugging and root cause analysis with both Codex (GPT-5.2) and Gemini.
When to Use
- Complex bugs requiring investigation
- Mysterious errors or failures
- Performance issues
- Race conditions or timing problems
- When user asks for debugging help from the council
Reasoning Level
xhigh (always - debugging requires deep analysis)
Execution
-
Gather all relevant context:
- Error messages
- Stack traces
- Relevant code files
- Logs if available
-
Formulate a debugging prompt:
Debug this issue systematically: Problem: <description of the bug> Error: <error message/stack trace> Relevant Code: <code snippets> Please: 1. Identify potential root causes 2. Analyze each possibility 3. Determine the most likely cause 4. Suggest a fix -
Run BOTH commands in parallel:
Codex:
bashcodex exec --sandbox read-only -c model_reasoning_effort="xhigh" "<prompt>"Gemini:
bashgemini -s -y -o json "<prompt>" -
Synthesize debugging insights
Response Format
## AI Council Debug Report
### Codex (GPT-5.2) Diagnosis:
**Potential Causes:**
1. [Cause with likelihood]
2. [Cause with likelihood]
**Root Cause Analysis:**
[Detailed analysis]
**Suggested Fix:**
[Code or steps to fix]
---
### Gemini Diagnosis:
**Potential Causes:**
1. [Cause with likelihood]
2. [Cause with likelihood]
**Root Cause Analysis:**
[Detailed analysis]
**Suggested Fix:**
[Code or steps to fix]
---
### Council Synthesis:
**Agreed Root Cause:** [If both agree]
**Conflicting Theories:** [If they differ]
**Recommended Fix:** [Synthesized fix strategy]
**Confidence Level:** [Based on agreement]
---
*Session IDs: Codex=[id], Gemini=[id]*
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?